Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names related to individuals involved in legal or medical cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaClair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juiz
    -0.47
     pescoço
    -0.45
     Irán
    -0.42
     médical
    -0.38
    muer
    -0.38
     klasik
    -0.38
     psicológico
    -0.37
     jurídica
    -0.37
     mijne
    -0.37
     bambú
    -0.36
    POSITIVE LOGITS
     Baillargeon
    0.66
    Šaltiniai
    0.62
     kaarangay
    0.62
     LeBlanc
    0.61
    avoie
    0.60
    RetentionPolicy
    0.57
    AndEndTag
    0.55
     Poi
    0.54
     MacDonald
    0.54
    RadioGroup
    0.53
    Act Density 0.095%

    No Known Activations